© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13953
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to participation or engagement

    oai_token-act-pair · gemini-2.0-flash

    participate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     participation
    -2.14
     Participation
    -1.97
     participating
    -1.88
    Participation
    -1.88
    particip
    -1.86
     participate
    -1.86
     PARTICIP
    -1.85
    participation
    -1.84
     participates
    -1.84
     involvement
    -1.77
    POSITIVE LOGITS
    ättä
    0.44
    roid
    0.41
    ctron
    0.40
    ICIAS
    0.40
    aca
    0.40
    תק
    0.40
    ACA
    0.40
    rong
    0.40
    hazi
    0.40
     vac
    0.39
    Activations Density 1.784%

    No Known Activations